{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:23:44Z","timestamp":1764782624421,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"Strategic Priority Research Program of the CAS","award":["XDB0680102"],"award-info":[{"award-number":["XDB0680102"]}]},{"name":"National Natural Science Foundation of China","award":["62472408,62441229"],"award-info":[{"award-number":["62472408,62441229"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFA1011602"],"award-info":[{"award-number":["2023YFA1011602"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,7]]},"DOI":"10.1145\/3767695.3769498","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:14:58Z","timestamp":1764782098000},"page":"331-336","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["C2T-ID: Converting Semantic Codebooks to Textual Document Identifiers for Generative Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3979-6069","authenticated-orcid":false,"given":"Yingchen","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-2541","authenticated-orcid":false,"given":"Ruqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2392-4946","authenticated-orcid":false,"given":"Wenjun","family":"Peng","sequence":"additional","affiliation":[{"name":"Researcher, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2124-953X","authenticated-orcid":false,"given":"Sen","family":"Li","sequence":"additional","affiliation":[{"name":"Researcher, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5918-093X","authenticated-orcid":false,"given":"Fuyu","family":"Lv","sequence":"additional","affiliation":[{"name":"Researcher, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-8195","authenticated-orcid":false,"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"31668","article-title":"Autoregressive search engines: Generating substrings as document identifiers","volume":"35","author":"Bevilacqua Michele","year":"2022","unstructured":"Michele Bevilacqua, Giuseppe Ottaviano, Patrick Lewis, Scott Yih, Sebastian Riedel, and Fabio Petroni. 2022. Autoregressive search engines: Generating substrings as document identifiers. Advances in Neural Information Processing Systems, Vol. 35 (2022), 31668-31683.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614821"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531827"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557271"},{"key":"e_1_3_2_1_5_1","volume-title":"Autoregressive entity retrieval. arXiv preprint arXiv:2010.00904","author":"Cao Nicola De","year":"2020","unstructured":"Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2020. Autoregressive entity retrieval. arXiv preprint arXiv:2010.00904 (2020)."},{"key":"e_1_3_2_1_6_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_8_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP (1). 6769-6781."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_10_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_12_1","volume-title":"Nonparametric decoding for generative retrieval. arXiv preprint arXiv:2210.02068","author":"Lee Hyunji","year":"2022","unstructured":"Hyunji Lee, Jaeyoung Kim, Hoyeon Chang, Hanseok Oh, Sohee Yang, Vlad Karpukhin, Yi Lu, and Minjoon Seo. 2022. Nonparametric decoding for generative retrieval. arXiv preprint arXiv:2210.02068 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_14_1","volume-title":"Generative cross-modal retrieval: Memorizing images in multimodal language models for retrieval and beyond. arXiv preprint arXiv:2402.10805","author":"Li Yongqi","year":"2024","unstructured":"Yongqi Li, Wenjie Wang, Leigang Qu, Liqiang Nie, Wenjie Li, and Tat-Seng Chua. 2024a. Generative cross-modal retrieval: Memorizing images in multimodal language models for retrieval and beyond. arXiv preprint arXiv:2402.10805 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Multiview identifiers enhanced generative retrieval. arXiv preprint arXiv:2305.16675","author":"Li Yongqi","year":"2023","unstructured":"Yongqi Li, Nan Yang, Liang Wang, Furu Wei, and Wenjie Li. 2023. Multiview identifiers enhanced generative retrieval. arXiv preprint arXiv:2305.16675 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28717"},{"key":"e_1_3_2_1_17_1","volume-title":"Updating transformer memory with new documents. arXiv preprint arXiv:2212.09744","author":"Mehta Sanket Vaibhav","year":"2022","unstructured":"Sanket Vaibhav Mehta, Jai Gupta, Yi Tay, Mostafa Dehghani, Vinh Q Tran, Jinfeng Rao, Marc Najork, Emma Strubell, and Donald Metzler. 2022. Dsi++: Updating transformer memory with new documents. arXiv preprint arXiv:2212.09744 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Codedsi: Differentiable code search. arXiv preprint arXiv:2210.00328","author":"Nadeem Usama","year":"2022","unstructured":"Usama Nadeem, Noah Ziems, and Shaoen Wu. 2022. Codedsi: Differentiable code search. arXiv preprint arXiv:2210.00328 (2022)."},{"key":"e_1_3_2_1_19_1","volume-title":"Generative retrieval as dense retrieval. arXiv preprint arXiv:2306.11397","author":"Nguyen Thong","year":"2023","unstructured":"Thong Nguyen and Andrew Yates. 2023. Generative retrieval as dense retrieval. arXiv preprint arXiv:2306.11397 (2023)."},{"key":"e_1_3_2_1_20_1","first-page":"9844","article-title":"Large Dual Encoders Are Generalizable Retrievers","author":"Ni Jianmo","year":"2022","unstructured":"Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hern\u00e1ndez \u00c1brego, Ji Ma, Vincent Y. Zhao, Yi Luan, Keith B. Hall, Ming-Wei Chang, and Yinfei Yang. 2022. Large Dual Encoders Are Generalizable Retrievers. In EMNLP. Association for Computational Linguistics, 9844-9855.","journal-title":"EMNLP. Association for Computational Linguistics"},{"key":"e_1_3_2_1_21_1","volume-title":"Zhuyun Dai, Siddhartha Brahma, Iftekhar Naim, Tao Lei, and Vincent Y Zhao.","author":"Qian Yujie","year":"2022","unstructured":"Yujie Qian, Jinhyuk Lee, Sai Meher Karthik Duddu, Zhuyun Dai, Siddhartha Brahma, Iftekhar Naim, Tao Lei, and Vincent Y Zhao. 2022. Multi-vector retrieval as sparse alignment. arXiv preprint arXiv:2211.01267 (2022)."},{"key":"e_1_3_2_1_22_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"Jing Liu, Hua Wu, Ji-Rong Wen, and Haifeng Wang.","author":"Ren Ruiyang","year":"2023","unstructured":"Ruiyang Ren, Wayne Xin Zhao, Jing Liu, Hua Wu, Ji-Rong Wen, and Haifeng Wang. 2023. TOME: A two-stage approach for model-based retrieval. arXiv preprint arXiv:2305.11161 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_26_1","first-page":"46345","article-title":"Learning to tokenize for generative retrieval","volume":"36","author":"Sun Weiwei","year":"2023","unstructured":"Weiwei Sun, Lingyong Yan, Zheng Chen, Shuaiqiang Wang, Haichao Zhu, Pengjie Ren, Zhumin Chen, Dawei Yin, Maarten Rijke, and Zhaochun Ren. 2023. Learning to tokenize for generative retrieval. Advances in Neural Information Processing Systems, Vol. 36 (2023), 46345-46361.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3653712"},{"key":"e_1_3_2_1_28_1","volume-title":"Generative Retrieval for Book Search. arXiv preprint arXiv:2501.11034","author":"Tang Yubao","year":"2025","unstructured":"Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Shihao Liu, Shuaiqing Wang, Dawei Yin, and Xueqi Cheng. 2025. Generative Retrieval for Book Search. arXiv preprint arXiv:2501.11034 (2025)."},{"key":"e_1_3_2_1_29_1","first-page":"21831","article-title":"Transformer memory as a differentiable search index","volume":"35","author":"Tay Yi","year":"2022","unstructured":"Yi Tay, Vinh Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Gupta, et al., 2022. Transformer memory as a differentiable search index. Advances in Neural Information Processing Systems, Vol. 35 (2022), 21831-21843.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_31_1","first-page":"25600","article-title":"A neural corpus indexer for document retrieval","volume":"35","author":"Wang Yujing","year":"2022","unstructured":"Yujing Wang, Yingyan Hou, Haonan Wang, Ziming Miao, Shibin Wu, Qi Chen, Yuqing Xia, Chengmin Chi, Guoshuai Zhao, Zheng Liu, et al., 2022. A neural corpus indexer for document retrieval. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25600-25614.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593590"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645477"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657746"},{"key":"e_1_3_2_1_35_1","volume-title":"European Conference on Computer Vision. Springer, 21-41","author":"Zhang Yidan","year":"2024","unstructured":"Yidan Zhang, Ting Zhang, Dong Chen, Yujing Wang, Qi Chen, Xing Xie, Hao Sun, Weiwei Deng, Qi Zhang, Fan Yang, et al., 2024. Irgen: Generative modeling for image retrieval. In European Conference on Computer Vision. Springer, 21-41."},{"key":"e_1_3_2_1_36_1","volume-title":"Ultron: An ultimate retriever on corpus with a model-based indexer. arXiv preprint arXiv:2208.09257","author":"Zhou Yujia","year":"2022","unstructured":"Yujia Zhou, Jing Yao, Zhicheng Dou, Ledell Wu, Peitian Zhang, and Ji-Rong Wen. 2022. Ultron: An ultimate retriever on corpus with a model-based indexer. arXiv preprint arXiv:2208.09257 (2022)."},{"key":"e_1_3_2_1_37_1","volume-title":"Bridging the gap between indexing and retrieval for differentiable search index with query generation. arXiv preprint arXiv:2206.10128","author":"Zhuang Shengyao","year":"2022","unstructured":"Shengyao Zhuang, Houxing Ren, Linjun Shou, Jian Pei, Ming Gong, Guido Zuccon, and Daxin Jiang. 2022. Bridging the gap between indexing and retrieval for differentiable search index with query generation. arXiv preprint arXiv:2206.10128 (2022)."}],"event":{"name":"SIGIR-AP 2025:Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Xi'an China","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:16:07Z","timestamp":1764782167000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767695.3769498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":37,"alternative-id":["10.1145\/3767695.3769498","10.1145\/3767695"],"URL":"https:\/\/doi.org\/10.1145\/3767695.3769498","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}